@article{wang2021ufo, title={UFO: A UniFied TransfOrmer for Vision-Language Representation Learning}, author={Wang, Jianfeng and Hu, Xiaowei and Gan, Zhe and Yang, Zhengyuan and Dai, Xiyang and Liu, Zicheng and Lu, Yumao and Wang, Lijuan}, journal={arXiv preprint arXiv:2111.10023}, year={2021} }